print ("Reading the training data...")
sys.stdout.flush()
TRAIN_DIR = "train/"
TEST_DIR = "test/"
# use HOG as a list of features
# reading in the data. This takes a while
train_imgs = utils.read_folder(TRAIN_DIR, 0, ntrain, flatten = False)
print ("\nDone!")
sys.stdout.flush()
print ("Getting HOG3 of the data...")
sys.stdout.flush()
# also takes a while
X = utils.getHOG3(train_imgs)
print ("\nDone!")
sys.stdout.flush()
X = np.insert(X, 0, 1.0, axis = 1)
theta = np.random.randn(X.shape[1], 10) * 0.0001
y = utils.read_labels('trainLabels.csv', 0, ntrain)
best_val = -1
best_softmax = None
X_train, X_val, y_train, y_val = cross_validation.train_test_split(X, y, test_size = 0.1)
print "y_train.shape=", y_train.shape
print "y_val.shape=", y_val.shape
print "X_train.shape=", X_train.shape
print "X_val.shape=", X_val.shape
sys.stdout.flush()
ntrain = 50000
print ("Reading the training data...")
sys.stdout.flush()
TRAIN_DIR = "train/"
# use HOG as a list of features
train_imgs = utils.read_folder(TRAIN_DIR, 0, ntrain, flatten = False)
print ("\nDone!")
sys.stdout.flush()
print ("Getting HOG3 of the data...")
sys.stdout.flush()
X = utils.getHOG3(train_imgs, cpb=(1,1))
print ("\nDone!")
sys.stdout.flush()
X = np.insert(X, 0, 1.0, axis = 1)
theta = np.random.randn(X.shape[1], 10) * 0.0001
y = utils.read_labels('trainLabels.csv', 0, ntrain)
best_val = -1
best_softmax = None
X_train, X_val, y_train, y_val = cross_validation.train_test_split(X, y, test_size = 0.1)
print "y_train.shape=", y_train.shape
print "y_val.shape=", y_val.shape
print "X_train.shape=", X_train.shape
print "X_val.shape=", X_val.shape
sys.stdout.flush()
